Wendy Device Interop

Organization

wendylabsinc

wendy-device-interop

Expert guidance on wendy-agent runtime interop with the SaaS stack: polling for changes, verifying operator-signed requests, and pulling images. Use when developers mention: (1) the postbox or device polling, (2) operator-signed change requests or desired state, (3) hash chains, checkpoints, or high-water marks, (4) applying deployments on devices, (5) image pull, wendy-proxy, or registries, (6) TSA or RFC 3161 timestamps, (7) fail-safe behavior on devices, (8) device mTLS to cloud.

Overview

Publisher	wendylabsinc
Repository	`claude-skills`
Skill name	`wendy-device-interop`
Stars	62
Forks	5
Bundled files	2
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by wendylabsinc on GitHub. Read the source before you install it.

Installation

Install the Wendy Device Interop AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/wendylabsinc/claude-skills/tree/main/wendy-device-interop
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/wendylabsinc/claude-skills.git /tmp/claude-skills
mkdir -p .claude/skills
cp -r /tmp/claude-skills/wendy-device-interop .claude/skills/wendy-device-interop

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wendy Device Interop in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wendy Device Interop on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wendy Device Interop is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Wendy Device Interop

wendy-agent's prime directive against the SaaS stack: apply a change only when it carries a valid operator signature the device can verify itself. Cloud is a queue, never an authority — it can accept, append, relay, and enforce, but it holds no key that lets it originate an authoritative change (§5.3, D3). Everything below flows from that one rule.

Hard Rules

Poll-only. The device polls cloud's postbox for changes; it never accepts a pushed change. There is no code path where cloud calls the device to mutate its state (§5.3).
Device presents its own mTLS cert. To cloud (postbox poll) and to wendy-proxy (image pull) alike, the device authenticates with its own hardware-backed certificate. Cloud never holds a certificate of its own to act as a principal (§5.3, §5.7).
No registry credential or token ever on-device. Images come only through wendy-proxy; the device never talks to a registry directly and never stores a pull credential (§5.7). wendy-proxy is planned, not live yet: see references/image-pull.md.
Independent verifiability. Nothing is applied on the strength of "cloud said so." Every change must be independently checkable by the device: valid operator signature, current freshness, and binding to this device — see references/postbox-verification.md for the full checklist.

Fail-Safe Catalogue

Condition	Response
Stale head checkpoint (past TTL, or below the device's high-water mark)	Don't trust the tail; alert (D8)
Unknown or too-stale trusted time	Hold current state; apply no time-gated change; alert (§4.4)
Unverifiable artifact or signature (chain link, checkpoint, request, or TSA token fails to verify)	Reject; alert
SaaS unreachable	Keep operating on held state (degraded mode) — never brick, never accept unverifiable material to stay "available"

Availability degrades. Security never does.

Audit

Every apply and verify outcome is emitted as a tamper-evident audit record, threaded by correlation_id so a single change can be traced across cloud, pki-core, and the device that applied it (§9 agent delta, §12).

Self-Hosted Rule (mandatory)

The wendy stack (wendyos / wendy-agent) must ALWAYS be able to run without the SaaS stack. Before shipping any interop change, consult the wendy-self-hosted skill: keep the self-hosted path intact, or create it where it doesn't exist yet. A SaaS-only feature is an incomplete feature.

Source of Truth

This skill distills the AAA Contract v0.21 (Approved 2026-08-29). The living contract lives in Linear: AAA Contract — Authentication, Authorization, Accounting. It is versioned and evolving: check it for flow-level detail, and if it disagrees with this skill, the contract wins — then update this skill.

Related Skills

wendy-aaa-interop — the full contract this skill distills a slice of.
wendy-device-enrollment — how the device got the mTLS cert it polls and pulls with.
wendy-security-baselines — the invariants any interop change must respect.
wendy-self-hosted — the standing dual-path rule.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Wendy Device Interop AI skill do?

Why use Wendy Device Interop on TypingMind?

Because you install it once and use it with any model. Wendy Device Interop is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wendy Device Interop in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wendylabsinc/claude-skills/tree/main/wendy-device-interop. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Wendy Device Interop?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wendy Device Interop?

As many as you like. As long as a model supports skills, you can use Wendy Device Interop with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wendy Device Interop AI skill free?

It is published on GitHub by wendylabsinc. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Openclaw Ghsa Maintainer

openclaw

OrganizationPopular

Inspect, patch, validate, publish, or confirm OpenClaw GHSA security advisories and private-fork state.

Openclaw Secret Scanning Maintainer

openclaw

OrganizationPopular

Triage, redact, clean up, and resolve OpenClaw GitHub Secret Scanning alerts in issues or PRs.

Release Openclaw Announcement

openclaw

OrganizationPopular

Draft or post OpenClaw beta, stable, or extended-stable Discord release announcements from changelog, tag, registry, and validation evidence. Use when announcing a release, release candidate, or…

Security Triage

Triage OpenClaw security advisories, drafts, and GHSA reports with shipped-tag and trust-model proof.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Wendy Device Interop

Hard Rules

Fail-Safe Catalogue

Audit

Self-Hosted Rule (mandatory)

Source of Truth

Related Skills

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now